INDEX

Explanations

legal, tax, company, country, issue

The neuron is primarily triggered by named entities—especially place and organization names (proper nouns).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 الجلد

-1.28

 блюдо

-1.23

 снова

-1.19

 сайті

-1.16

 ของ

-1.13

 planific

-1.12

Subset

-1.09

 everybody

-1.09

 this

-1.07

 desmotiv

-1.06

POSITIVE LOGITS

וּ

1.51

 countries

1.34

 foreign

1.31

營業時間

1.30

κει

1.26

 речо

1.26

័

1.24

 musuh

1.22

ghalaya

1.21

 extranjera

1.19

Activations Density 0.015%